Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9572
    Prev
    Next
    INDEX
    Explanations

    keywords related to gold

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gold and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    -0.82
    zee
    -0.79
     Romance
    -0.69
    ally
    -0.65
    ========
    -0.64
    onomous
    -0.63
    ================================================================
    -0.62
     reperto
    -0.62
     Consent
    -0.62
     Eliot
    -0.61
    POSITIVE LOGITS
    vertisement
    1.26
    smith
    1.25
    fish
    1.13
     medal
    1.11
    mine
    1.05
     coins
    1.04
    rush
    0.99
     medals
    0.96
    mining
    0.92
    mund
    0.90
    Activations Density 0.027%

    No Known Activations